DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B
LoRA-style vs DavidAU/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 55 of 55 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/221, MLP 165/165, Attention 217/220
3 derivatives checked
- DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B-NEO-Horror-Imatrix-GGUF: Quantization
- mradermacher/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B-i1-GGUF: Quantization
- mradermacher/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B-GGUF: Same weights, converted